A three-stage bearing transfer fault diagnosis method for large domain shift scenarios

In recent years, significant progress has been achieved in the intelligent fault diagnosis of bearings based on transfer learning. However, existing methods overlook the presence of domain-specific features that are non-transferable when aligning domain distributions. Additionally, the reliability of subdomain alignment has not been adequately evaluated. This severely restricts the diagnostic performance of transfer learning, especially in scenarios of large domain shifts. To address these issues, this paper proposes a novel approach based on three-stage transfer alignment. In the first stage, two private encoders, and a shared encoder are designed to eliminate domain-specific features, thus maximizing the effectiveness and transferability of shared encoded features. Subsequently, in the second stage, a deep adversarial domain adaptation method is introduced to adapt the global distributions between the two domains. Lastly, the third stage presents a novel soft pseudo-label distillation method, based on adaptive entropy weighting. This enhances alignment between subdomains, further bridging the distribution gap between the two domains. A series of comprehensive experiments under two types of large domain shift scenarios validate that the proposed method has a superior performance and could boost 6.93 % and 6.14 % accuracy than the state-of-the-art methods, respectively.